playwright-e2e-mcp
# playwright-e2e-mcp has moved
This repository is no longer maintained. **playwright-e2e-mcp now lives at
[github.com/xsignon-secure/E2E](https://github.com/xsignon-secure/E2E).**
The latest release is **0.4.2**. To set it up in your project:
```bash
npx -y playwright-e2e-mcp init
```
The npm package name is unchanged, so existing installs keep working; run the command above
(or `npm install -D playwright-e2e-mcp@latest`) to pick up the newest version.
Issues, pull requests, releases and the `.mcpb` Claude Desktop bundle are all at the new home:
- Repository: https://github.com/xsignon-secure/E2E
- Releases: https://github.com/xsignon-secure/E2E/releases
- MCP Registry name: `io.github.xsignon-secure/E2E`
playwright-e2e-mcp is, and stays, fully open source and free under the MIT license.
TDQS
Scored across 11 tools
Tools map to distinct stages of the Playwright workflow: listing, running, monitoring, failure analysis, fixing, generation, visual comparison, selector validation, flaky diagnosis, and history. Overlap exists between diagnose-flaky and analyze-history, and between get-failure and get-run-status, but descriptions clarify the boundaries.
All tool names use kebab-case with a consistent verb-first pattern (run-test, get-failure, list-tests, validate-selector, etc.). Minor variation in noun length does not break the convention.
11 tools is well within the ideal 3–15 range. Each tool addresses a distinct aspect of Playwright E2E testing without obvious redundancy.
The core lifecycle is well covered: list tests, run tests, monitor runs, analyze failures, suggest fixes, generate tests, validate selectors, compare visual state, diagnose flakiness, and analyze history. Minor gaps include running a specific test or reading a single test's code, but agents can work around these.